|
Activity Number:
|
540
- SPEED: Clinical Trial Design, Longitudinal Analysis, and Other Topics in Biopharmaceutical Statistics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2018 : 11:35 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #332697
|
|
|
Title:
|
MMRM Estimates Consideration for Longitudinal Data in Clinical Trials
|
|
Author(s):
|
Zheng (Jason) Yuan and Yaohua Zhang* and Chenkun Wang and Bingming Yi
|
|
Companies:
|
Vertex Pharmaceuticals and Vertex Pharmaceuticals and Vertex Pharmaceuticals
|
|
Keywords:
|
MMRM;
Longitudinal;
Clinical Trials;
Estimate;
Mixed
|
|
Abstract:
|
When analyzing longitudinal data in clinical trials, it is common to implement Mixed-effect Model Repeat Measurement (MMRM) to estimate least-square (LS) means and standard errors (SEs). However, caution needs to be taken when categorical covariates and/or imbalanced covariates are included in the data as the LS mean estimates obtained could be inappropriate in randomized clinical trials. The issues of traditional "LSMEANS" approach in SAS include: (1) may generate bias and sometimes far deviation from naïve means, causing difficult interpretation; (2) may generate different results when adding interaction term between covariates and treatment group, as compared to that without interaction term; (3) give larger standard error estimates leading to reduced power. We explore and evaluate these issues by both simulations and clinical trial examples and propose a more efficient and flexible approach by using "ESTIMATE statement" in SAS. The simulation results show that the proposed approach provides less unbiased and more efficient estimates than the traditional "LSMEANS" approach. The proposed approach is also applied to a real-world clinical trial study to demonstrate its performance.
|
Authors who are presenting talks have a * after their name.
